Search

PythonReactSEOPDF
OpenClaw

Vincent - Trading Engine for agents

Strategy-driven automated trading for Polymarket and HyperLiquid. Use this skill when users want to create trading strategies, set stop-loss/take-profit/trailing stop rules, or manage automated trading. Triggers on "trading strategy", "stop loss", "take profit", "trailing stop", "automated trading", "trading engine", "trade rules", "strategy monitor".

glitch0030 source installs☆ 0 Repository starsv1.0.0

Installation

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.

SkillHub CLI

skillhub install glitch003/vincent-trading-engine

Inspect the source and compatibility requirements, then follow its installation steps.

Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.

View source ↗Guides

Skill instructions

Vincent Trading Engine - Strategy-Driven Automated Trading

Use this skill to create and manage automated trading strategies for Polymarket prediction markets and HyperLiquid perpetuals/spot. The Trading Engine combines driver-based monitoring (web search, Twitter, newswire, price feeds) with a signal pipeline and LLM-powered decision-making to automatically trade based on your thesis. It also includes standalone stop-loss, take-profit, and trailing stop rules that work without the LLM.

All commands use the @vincentai/cli package.

How It Works

The Trading Engine is a unified system with two modes:

  1. LLM-Powered Strategies — Create a versioned strategy with a structured thesis, weighted drivers (web search keywords, Twitter accounts, newswire topics, price triggers), and an escalation policy. When drivers detect new information, signals are scored and batched. When the escalation threshold is met, an LLM (Claude via OpenRouter) evaluates the signals against your thesis and decides whether to trade, update the thesis, set protective orders, or alert you.
  2. Standalone Trade Rules — Set stop-loss, take-profit, and trailing stop rules on positions. These execute automatically when price conditions are met — no LLM involved.

Architecture:

  • Integrated into the Vincent backend (no separate service to run)
  • Strategy endpoints under /api/skills/polymarket/strategies/...
  • Trade rule endpoints under /api/skills/polymarket/rules/...
  • HyperLiquid rules use venue: "hyperliquid" and route through the HL adapter
  • Uses the same API key as the Polymarket or HyperLiquid skill (depending on venue)
  • All trades go through Vincent's policy-enforced pipeline
  • LLM costs are metered and deducted from the user's credit balance
  • Every LLM invocation is recorded with full audit trail (tokens, cost, actions, duration)

Security Model

  • LLM cannot bypass policies — all trades go through the venue's policy-enforced skill (`polymarketSkill.placeBe...

Source information

Source
github
Repository
openclaw/skills
Path
skills/glitch003/vincent-trading-engine
Version
1.0.0
Commit
22b4e7c6fb56c7c64897458aa213afcd499fa27f
Classification source
rules
Status
active
Visibility
public

These signals come from indexed source analysis and may lag behind changes. Check the current source files.

Extracted content

SKILL.md
# Vincent Trading Engine - Strategy-Driven Automated Trading

Use this skill to create and manage automated trading strategies for Polymarket prediction markets and HyperLiquid perpetuals/spot. The Trading Engine combines driver-based monitoring (web search, Twitter, newswire, price feeds) with a signal pipeline and LLM-powered decision-making to automatically trade based on your thesis. It also includes standalone stop-loss, take-profit, and trailing stop rules that work without the LLM.

All commands use the `@vincentai/cli` package.

## How It Works

**The Trading Engine is a unified system with two modes:**

1. **LLM-Powered Strategies** — Create a versioned strategy with a structured thesis, weighted drivers (web search keywords, Twitter accounts, newswire topics, price triggers), and an escalation policy. When drivers detect new information, signals are scored and batched. When the escalation threshold is met, an LLM (Claude via OpenRouter) evaluates the signals against your thesis and decides whether to trade, update the thesis, set protective orders, or alert you.
2. **Standalone Trade Rules** — Set stop-loss, take-profit, and trailing stop rules on positions. These execute automatically when price conditions are met — no LLM involved.

**Architecture:**

- Integrated into the Vincent backend (no separate service to run)
- Strategy endpoints under `/api/skills/polymarket/strategies/...`
- Trade rule endpoints under `/api/skills/polymarket/rules/...`
- HyperLiquid rules use `venue: "hyperliquid"` and route through the HL adapter
- Uses the same API key as the Polymarket or HyperLiquid skill (depending on venue)
- All trades go through Vincent's policy-enforced pipeline
- LLM costs are metered and deducted from the user's credit balance
- Every LLM invocation is recorded with full audit trail (tokens, cost, actions, duration)

## Security Model

- **LLM cannot bypass policies** — all trades go through the venue's policy-enforced skill (`polymarketSkill.placeBe...

Related skills

OpenClaw

xint

0xnyk

X Intelligence CLI — search, monitor, analyze, and engage on X/Twitter. TypeScript + Bun. AI agent skill.

OpenClaw

bambu-studio-ai

heyixuan2

Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...

OpenClaw

flightclaw

jackculpan

Track flight prices from Google Flights with this OpenClaw skill. Search routes, monitor prices, and get alerts when prices drop.

OpenClaw

openclaw-trading-assistant

openclaw-trade

openclaw trading assistant| openclaw trading skill | nof1.ai & openclaw [moltbot] collaboration | We get the best practices from alpha arena trading seasons and bring it to clawdbot All top AI agents, realtime...